Competitive learning vector quantization with evolution strategies for image compression

Shuangteng Zhang; Ezzatollah Salari

首页> 外文期刊>Optical Engineering >Competitive learning vector quantization with evolution strategies for image compression

【24h】

Competitive learning vector quantization with evolution strategies for image compression

机译：Competitive learning vector quantization with evolution strategies for image compression

获取原文

获取原文并翻译 | 示例

掌桥外文数据库（机构版） >>

开具论文收录证明 >>

文献代查 >>

页面导航

摘要
著录项
相关主题

摘要

We present a competitive learning vector quantization with evolution strategies for image compression. This technique embeds evolution strategies (ES) into the standard competitive learning vector quantization algorithm (CLVQ). After each iteration during the CLVQ training process, the so-far generated codebook is adjusted by the embedded ES through its recombination, mutation, and selection process. The proposed algorithm can efficiently overcome CLVQ's problems of under-utilization of neurons and initial codebook dependency. The embedding of ES greatly increases the algorithm's capability to avoid local minimums, leading to a global optimization. Experimental results demonstrate that it can obtain significant improvement over CLVQ and other comparable algorithms in image compression applications, especially when it involves larger codebooks.

著录项

来源
《Optical Engineering》 |2005年第2期|027006-1-027006-8-0|共8页
作者
Shuangteng Zhang; Ezzatollah Salari;
展开▼
作者单位

Eastern Kentucky University Department of Computer Science Richmond, Kentucky 40475;

展开▼
收录信息美国《科学引文索引》(SCI);美国《工程索引》(EI);
原文格式 PDF
正文语种英语
中图分类光学仪器;
关键词
vector quantization; neural networks; competitive learning; evolution strategies; codebook generation;

Competitive learning vector quantization with evolution strategies for image compression

摘要

著录项

相关主题

期刊订阅